Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 4 of 4 for 20x28xi8 (0.09 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/post-quantize.mlir 

        :  ( tensor<1x28x28x!quant.uniform<i8:f32, 0.003:-128>>,
         tensor<20x28x!quant.uniform<i8:f32, 0.006:-34>>, tensor<20x28x!quant.uniform<i8:f32, 0.006:-34>>, tensor<20x28x!quant.uniform<i8:f32, 0.006:-34>>, tensor<20x28x!quant.uniform<i8:f32, 0.006:-34>>,
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 19.9K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/tf2xla/tests/legalize-tf-quant.mlir 

      // CHECK: %[[CONVERT_1:.*]] = mhlo.bitcast_convert %[[QUANTIZE]] : (tensor<2x2x!quant.uniform<i8:f32:0, {1.000000e+00:3,2.000000e+00:4}>>) -> tensor<2x2xi8>
  // CHECK: %[[CONVERT_2:.*]] = mhlo.bitcast_convert %[[CONVERT_1]] : (tensor<2x2xi8>) -> tensor<2x2x!quant.uniform<i8:f32:0, {1.000000e+00:3,2.000000e+00:4}>>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 09 01:25:29 UTC 2024
    - 37.3K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/quantize.mlir 

      func.return %1 : tensor<2x2x!quant.uniform<u8:f32, 7.8431372549019615E-4:128>>

// CHECK:  %[[cst:.*]] = "tfl.pseudo_qconst"() <{qtype = tensor<2x2x!quant.uniform<u8:f32, 7.8431372549019615E-4:128>>, value = dense<0> : tensor<2x2xi8>}>
// CHECK:  return %[[cst]]
}

// CHECK-LABEL: QuantizeFloatConst4Bits
func.func @QuantizeFloatConst4Bits() -> tensor<2x4x!quant.uniform<i4:f32, 2.500000e-01:-1>> {
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue May 28 23:10:13 UTC 2024
    - 39.7K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/tests/prepare-quantize.mlir 

    func.func @DequantizeAndQuantize() -> tensor<2x2x!quant.uniform<u8:f32, 7.8431372549019615E-4:128>> {
  %cst = "tfl.pseudo_qconst"() {qtype = tensor<2x2x!quant.uniform<u8:f32, 7.8431372549019615E-4:128>>, value = dense<-1> : tensor<2x2xi8>} : () -> tensor<2x2x!quant.uniform<u8:f32, 7.8431372549019615E-4:128>>
  %0 = "tfl.dequantize"(%cst) : (tensor<2x2x!quant.uniform<u8:f32, 7.8431372549019615E-4:128>>) -> tensor<2x2xf32>
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu May 02 09:41:17 UTC 2024
    - 67.5K bytes
    - Viewed (0)
Back to top